Relatório 1 - trabalhar as questões de pesquisa com o R

Dataset: World Happiness Report Link: https://www.kaggle.com/unsdsn/world-happiness

data(worldgeojson)
df15 <- read.csv("/home/christiano/Dropbox/trabalhos/disciplina_mineracao/datasets/datasets_menores/world-happines/2015.csv", stringsAsFactors = FALSE)
df16 <- read.csv("/home/christiano/Dropbox/trabalhos/disciplina_mineracao/datasets/datasets_menores/world-happines/2016.csv", stringsAsFactors = FALSE)
df17 <- read.csv("/home/christiano/Dropbox/trabalhos/disciplina_mineracao/datasets/datasets_menores/world-happines/2017.csv", stringsAsFactors = FALSE)

RQ1 Quais países que apresentaram as melhores evoluções e as piores quedas no score de felicidade entre 2015 e 2017

df1<-merge(df15[,c(1,3)],
           df16[,c(1,3)],
           by.x = "Country",
           by.y = "Country")
df1<-merge(df1,
           df17[,c(1,2)],
           by.x = "Country",
           by.y = "Country")
colnames(df1)<-c("Country","2015","2016","2017")
df1<-df1%>%
  mutate(rank_change=`2017`-`2015`)
asc <- df1[order(df1$rank_change),]
desc <- df1[order(df1$rank_change,decreasing = TRUE),]
dfBestChanges <- desc[1:3,]
dfWorstChanges <- asc[1:3,]
dfBestChanges

dfWorstChanges

dfBestWortC <- rbind(dfBestChanges, dfWorstChanges)
dfBestWortC <- dfBestWortC[,c(-6)]
dfRank2015 <- data.frame(country=dfBestWortC$Country,rank=dfBestWortC$`2015`,ano="2015")
dfRank2016 <- data.frame(country=dfBestWortC$Country,rank=dfBestWortC$`2016`,ano="2016")
dfRank2017 <- data.frame(country=dfBestWortC$Country,rank=dfBestWortC$`2017`,ano="2017")
dfRank <- rbind(dfRank2015,dfRank2016)  
dfRank <- rbind(dfRank,dfRank2017)  
dfRank %>% ggplot(aes(ano,rank,group=country)) + geom_line(aes(color=country)) + geom_point() + geom_label(aes(label=rank)) 

#desc[1:5,c(1,5)] %>% ggplot(aes(Country,rank_change)) + geom_bar(stat = "identity")

str(dataset)

'data.frame':   158 obs. of  12 variables:
 $ Country                      : Factor w/ 158 levels "Afghanistan",..: 136 59 38 106 25 46 100 135 101 7 ...
 $ Region                       : Factor w/ 10 levels "Australia and New Zealand",..: 10 10 10 10 6 10 10 10 1 1 ...
 $ Happiness.Rank               : int  1 2 3 4 5 6 7 8 9 10 ...
 $ Happiness.Score              : num  7.59 7.56 7.53 7.52 7.43 ...
 $ Standard.Error               : num  0.0341 0.0488 0.0333 0.0388 0.0355 ...
 $ Economy..GDP.per.Capita.     : num  1.4 1.3 1.33 1.46 1.33 ...
 $ Family                       : num  1.35 1.4 1.36 1.33 1.32 ...
 $ Health..Life.Expectancy.     : num  0.941 0.948 0.875 0.885 0.906 ...
 $ Freedom                      : num  0.666 0.629 0.649 0.67 0.633 ...
 $ Trust..Government.Corruption.: num  0.42 0.141 0.484 0.365 0.33 ...
 $ Generosity                   : num  0.297 0.436 0.341 0.347 0.458 ...
 $ Dystopia.Residual            : num  2.52 2.7 2.49 2.47 2.45 ...

RQ2 Qual o rank dos países obtiveram a média dos melhores scores de felicidade

RQ3 Quais features influenciam no score de felicidade

test<-cor(as.matrix(df15[,-c(1,2,3)]))
test2<-cor(as.matrix(df16[,-c(1,2,3)]))
corrplot::corrplot(test,method = "square",type = "upper",mar = c(0,0,1,0))

corrplot::corrplot(test2,type = "upper",method = "square",mar = c(0,0,1,0))

RQ4

plot_ly(df16,x=~Region,
        y=~Happiness.Score,
        type="box",
        boxpoints="all",
        pointpos = -1.8,
        color=~Region)%>%
  layout(xaxis=list(showticklabels = FALSE),
         margin=list(b = 100))

n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

RQ5